Videos

FLOWERS just opened a video channel on Youtube, available here.

Robots and experiments

ICub learning to recognize visual objects through curiosity-driven manipulation. Read more...

This work addresses the problem of active object learning by a humanoid child-like robot, using a developmental approach. We propose a cognitive architecture where the visual representation of the objects is built incrementally through active exploration. We present the design guidelines of the cognitive architecture, its main functionalities, and we outline the cognitive process of the robot by showing how it learns to recognize objects in a human-robot interaction scenario inspired by social parenting. The robot actively explores the objects through manipulation, driven by a combination of social guidance and intrinsic motivation. Besides the robotics and engineering achievements, our experiments replicate some observations about the coupling of vision and manipulation in infants, particularly how they focus on the most informative objects.

Object Learning Through Active Exploration
Ivaldi, S., Nguyen, M., Lyubova, N., Droniou, A., Padois, V., Filliat, D., Oudeyer, P-Y., Sigaud, O. (in press)
IEEE Transactions on Autonomous Mental Development
https://flowers.inria.fr/ActiveExplor…

ANR Project MACSi: http://macsi.isir.upmc.fr/index.php?p…
Partners: ISIR at Univ Paris VI, Ensta ParisTech, Flowers at Inria, GOSTAI

Curiosity-driven development of locomotion in a quadruped robot. Read more...

Curiosity-driven learning of locomotion. Driven by intrinsic motivation, the robot explores how movements of its legs make its whole body move around. Initially, he has no knowledge of its own body and of the environment (but his body has a bio-inspired morphology and motor primitives, which provide initial structure). He is not programmed to learn specific movements such as going forward or turning on the right or left, but rather chooses to experiment what he finds “interesting”: he is self-motivated to explore movements which produce “learning progress”, i.e. which allows it to improve its knowledge or its skills per se. At the beginning, movements are somewhat random. Then, they robot focuses on certain kinds of movements which produce initially high-learning progress, such as walking backwards. Then, it focuses on learning movements that make it walk a bit like a crab and turn. Finally, he explores and learn movements that make it crawl forward.

Oudeyer P-Y, Kaplan , F. and Hafner, V. (2007) Intrinsic Motivation Systems for Autonomous Mental Development, IEEE Transactions on Evolutionary Computation, 11(2), pp. 265–286.
http://www.pyoudeyer.com/ims.pdf

Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots,
Baranes, A., Oudeyer, P-Y. (2013)
Robotics and Autonomous Systems, 61(1), pp. 49-73.http://www.pyoudeyer.com/ActiveGoalEx…

The Acroban Humanoid: an Overview. Read more...

Acroban is a lightweight compliant humanoïd robot. It is capable of semi-passive dynamic movement, including semi-passive dynamic walking. Equipped with a multi-articulated vertebral column, its bio-inspired design relies heavily on the use of adequate morphology and materials for robustness and adaptivity to external perturbations. This allows not only for advanced motor skills, but also affords a new kind of physical human-robot interaction which is
made possible by the ability of the human to modify the state (joint positions) of the robot by a direct physical manipulation, thanks to compliance. In this way, joints become the interface between the robot and the human: They make possible the exchange of analogical information. Interestingly, the motors, material, and electronics of Acroban are all low-cost. This allows us to show that it is actually possible to build such robust compliant motor skills and generate original life-like movements with basic affordable components if they are adequately chosen, combined and controlled.

Furthermore, Acroban provokes spontaneous highly positive emotional reactions, especially in children. Yet, as opposed to many other robots, its morphology is neither roundish nor cute. He has no big eyes. He is just made of metal, and its appearance shows it explicitly. At first glance, its visual appearance creates low expectation of intelligence and life-likeness. But when it begins to move and one can touch it, its natural dynamics, much more life-like than most other robots, triggers a high contrast and positive surprise. Life unexpectedly appears out of a neutral metallic object, much as Pixar’s Luxo Jr. This is the Luxo Jr. effect.

After a live demonstration of Acroban at Siggraph 2010 Emerging Technologies, a new demonstration will happen in Europe at INNOROBO, the International Summit of Robotic Innovation in march 2011, http://www.innorobo.com

Ly, O., Oudeyer, P-Y. (2010) Acroban the Humanoid: Playful and Compliant Physical Child-Robot Interaction, in ACM SIGGRAPH’2010 Emerging Technologies.

Acroban is the result of a collaboration between INRIA FLOWERS and Université Bordeaux I/Labri.

More info on: http://flowers.inria.fr/acroban.php

Curiosity driven learning in The Playground Experiment: From Affordances to Communication. Read more...

The Playground Experiment explores how mechanisms of intrinsically motivated learning, also called curiosity‐driven exploration, can self‐organize developmental trajectories, starting from discovery of the body, then going through the discovery of object affordances, and then going from vocal babbling to vocal interactions with others.

In such curiosity-driven exploration, the robot is motivated to explore sensorimotor activities for which it is making learning progress: i.e. its estimated performances in prediction or in mastery are increasing (and thus uncertainty is decreasing).
Thus, there is an intrinsic reward for learning progress, managed by a meta‐cognitive structure which then allows the learner to order autonomously its own learning experiences, creating its own curriculum where skills, including the manipulation of external objects, progressively increase in complexity.

In particular, such experiments suggest that the onset of language can spontaneously forms out of such sensorimotor development, where vocalizations are discovered by the learner to be special forms of “tools” that allow to manipulate a special kind of external entities, i.e. others (as a side effect, the meta-cognitive system is itself forming internal distinctive categories of “self” vs. “physical objects” vs. “others”, based on how much they create learnable interactions).

References:
Gottlieb, J., Oudeyer, P‐Y., Lopes, M., Baranes, A. (in press) Information seeking, curiosity and attention: computational and neural mechanisms, Trends in Cognitive Science.

Oudeyer P-Y, Kaplan , F. and Hafner, V. (2007) Intrinsic Motivation Systems for Autonomous Mental Development, IEEE Transactions on Evolutionary Computation, 11(2), pp. 265–286.
http://www.pyoudeyer.com/ims.pdf

Oudeyer, P‐Y., Kaplan, F. (2006) Discovering communication, Connection Science, 18(2), pp. 189‐‐206.
http://www.pyoudeyer.com/ConnectionSc…

The Impact of Human-Robot Interfaces on the Learning of Visual Objects. Read more...

Rouanet, P., Oudeyer, P-Y., Danieau, F., Filliat, D. (2013) The Impact of Human-Robot Interfaces on the Learning of Visual Object, IEEE Transactions on Robotics, 29(2), pp. 525-541.

https://flowers.inria.fr/TRO-12-Rouan…

This paper studies the impact of interfaces, allowing nonexpert users to efficiently and intuitively teach a robot to rec- ognize new visual objects. We present challenges that need to be addressed for real-world deployment of robots capable of learning new visual objects in interaction with everyday users. We argue that in addition to robust machine learning and computer vision meth- ods, well-designed interfaces are crucial for learning efficiency. In particular, we argue that interfaces can be key in helping non-expert users to collect good learning examples and, thus, improve the performance of the overall learning system.

Then, we present four alternative human–robot interfaces: Three are based on the use of a mediating artifact (smartphone, wiimote, wiimote and laser), and one is based on natural human gestures (with a Wizard-of-Oz recognition system). These interfaces mainly vary in the kind of feedback provided to the user, allowing him to understand more or less easily what the robot is perceiving and, thus, guide his way of providing training examples differently.

We then evaluate the impact of these interfaces, in terms of learning efficiency, usability, and user’s experience, through a real world and large-scale user study. In this experiment, we asked participants to teach a robot 12 different new visual objects in the context of a robotic game. This game happens in a home-like environment and was de- signed to motivate and engage users in an interaction where using the system was meaningful. We then discuss results that show significant differences among interfaces. In particular, we show that interfaces such as the smartphone interface allows nonexpert users to intuitively provide much better training examples to the robot, which is almost as good as expert users who are trained for this task and are aware of the different visual perception and machine learning issues. We also show that artifact-mediated teaching is significantly more efficient for robot learning, and equally good in terms of usability and user’s experience, than teaching thanks to a gesture-based human-like interaction.

The Ergo-Robot Experiment: Artificial Curiosity and Language Formation in Robots Read more...

The Ergo-Robot Experiment: Artificial Curiosity and Language Formation in Robots

Presentation of the Ergo-Robot Experiment by Pierre-Yves Oudeyer, during “Symposium on Language Acquisition and Language Evolution”, Stockholm University, Royal Academy of Sciences, Stockholm, Sweden (organised by Francesco Lacerda and Bjorn Lindblom).

=== Summary

In a big egg that has just opened, a tribe of young robotic creatures evolves and explores its environment, wreathed by a large zero that symbolizes the “origin.” Beyond their innate capabilities, they are outfitted with mechanisms that allow them to learn new skills and invent their own language. Endowed with artificial curiosity, they explore objects around them, as well as the effect their vocalizations produce on humans. Human, also curious to see what these creatures can do, react with their own gestures, creating a loop of interaction which progressively self-organizes into a new communication system established between man and ergo-robots.

The Ergo-Robot Experiment addresses a very important methodological and experimental need in Developmental Robotics: evaluating how algorithmic architectures for learning and development can scale up to long-term real world robot experiments (i.e. robot operating and learning continuously for several weeks or months). For this goal, which Ergo-Robots addresses [P28], and in the context of a research lab, one needs an experimental platform which is very robust, with precise and reliable motor control, easy to use and maintain, relatively cheap, and reconfigurable (in order to evaluate algorithms on robots with different morphologies, i.e. different robots).

The experiment was presented at the exhibition “Mathematics: A Beautiful Elsewhere” at Fondation Cartier pour l’Art Contemporain (scenography made in collaboration with film director David Lynch) provided in itself a large impact for scientific dissemination of our research activities towards the general public, being explained by student scientific mediators to around 70000 visitors (trained students were continuously present in the exhibition), and being reported multiple times in the general press (e.g. France 2, France Inter, France Culture, RFI, BFM TV, Slate.fr, Sciences et Avenir, New Scientist, Financial Times).

ts software and hardware development was realized by the INRIA ENSTA ParisTech Flowers team in collaboration with University of Bordeaux/Labri: Jérome Béchu, Fabien Bénureau, Haylee Fogg, Paul Fudal, Hugo Gimbert, Matthieu Lapeyre, Olivier Ly, Olivier Mangin, Pierre-Yves Oudeyer, Pierre Rouanet. Scenography was realized in collaboration with David Lynch and his team. Scenography was realiszed in collaboration with David Lynch and his team.

=== Main references

Web site: https://flowers.inria.fr/robots/ergo-robots/

Oudeyer, P-Y. (2011) Curiosity and Languages, in Catalogue of the Exhibition “Mathematics: A Beautiful Elsewhere”, Fondation Cartier pour l’Art Contemporain, Paris, France.

https://flowers.inria.fr/OudeyerCatalogueExpoMathematics2011GB.pdf

Oudeyer P-Y, Kaplan , F. and Hafner, V. (2007) Intrinsic Motivation Systems for Autonomous Mental Development, IEEE Transactions on Evolutionary Computation, 11(2), pp. 265–286.

http://www.pyoudeyer.com/ims.pdf

Steels, L. (2003) Evolving grounded communication for robots. Trends in Cognitive Science. 7(7), July 2003, pp. 308-312.

http://www.csl.sony.fr/downloads/papers/2003/steels-03c.pdf

Gottlieb, J., Oudeyer, P-Y., Lopes, M., Baranes, A. (2013)
Trends in Cognitive Science, 17(11), pp. 585-596. http://dx.doi.org/10.1016/j.tics.2013.09.001


Talks and interviews (english)

TedX Talk: Fabricating Open-Source Baby Robots

TedXTalk given by Pierre-Yves Oudeyer, published in sept. 2014.

What can baby robots tell us about ourselves? Mysteries of human cognition, like the mechanisms of curiosity or the origins of languages, are starting to be unveiled through experiments with robots that can learn by themselves. Pierre-Yves Oudeyer, research director and laureate of the prestigious European Research Council (ERC) program, introduces the Poppy open-source 3D printed humanoid robot made at Inria, allowing every lab, school or FabLab to join this open science exploration.

Self-Organization and Developmental Mechanisms in the Origins of Speech and Action Systems. Read more ...

 Self-Organization and Developmental Mechanisms in the Origins of Speech and Action Systems

Invited talk of Pierre-Yves Oudeyer at “Symposium on Language Acquisition and Language Evolution”, Stockholm University, Royal Academy of Sciences, Stockholm, Sweden (organised by Francesco Lacerda and Bjorn Lindblom). 2011.

=== Main references:

Oudeyer, P-Y. (2006) Self-Organization in the Evolution of Speech, Oxford University Press. Bibtex (Translated by James R. Hurford.)

http://www.pyoudeyer.com/originsOfSpeech.htm

Oudeyer P-Y, Kaplan , F. and Hafner, V. (2007) Intrinsic Motivation Systems for Autonomous Mental Development, IEEE Transactions on Evolutionary Computation, 11(2), pp. 265–286.

http://www.pyoudeyer.com/ims.pdf

Oudeyer P-Y., Smith L. (in preparation) How Evolution may work through Curiosity-driven Developmental Process.

Further information: http://www.pyoudeyer.com

=== Summary:

What is the origins of speech? How speech systems of languages form and evolve? How a child learns speech?

Can robots invent and learn their own vocalisation system? How constructing robot can help us understand better humans?

I study these questions in this talk, following a systemic approach, where the problem is approached globally. I gather human sciences, natural sciences and computational sciences within the same laboratory of ideas to explore the origins of language.

I draw some parallels with the formation of biological structures like bee hives and shell shapes, and explore how self-organisation, in interaction with natural selection, can explain important aspects of the morphogenesis of speech.

In particular, I present robotic experiments in which a population of individuals, with models of the vocal tract and the auditory system, invent, form and negotiate its own system of combinatorial vocalisations, through local peer-to-peer interactions. I compare the emergent systems with human sound systems, and show that strong similarities can be observed.

I also discuss how, in the course of individual cognitive development, babbling and vocal imitation can themselves self-organise, resulting from a mechanism of curiosity, an intrinsic motivation which pushes the newborn to discover its own body and its relations with the environment for the pure pleasure of learning.

In this context, and from new perspectives on artificial intelligence, I explain how it is possible to model mechanisms of curiosity allowing a robot to explore its own body and its physical and social interactions with the environment.

Thus new scientific maps appear, and show us stimulating paths to the origins of speech.

Learning to Interpret Unknown Teaching Signals: An Introduction - Part 1 : Introduction. Read more...

Robot Learning Simultanously a Task and How to Interpret Human Instructions

Grizou, J., Lopes, M. and Oudeyer, P-Y. (2013)
Proceedings of IEEE International Conference on Development and Learning and Epigenetic Robotics, IEEE ICDL-Epirob, Osaka, Japan.
http://hal.archives-ouvertes.fr/docs/…

Learning to Interpret Unknown Teaching Signals: An Introduction - Part 2. Read more...

Robot Learning Simultanously a Task and How to Interpret Human Instructions
Grizou, J., Lopes, M. and Oudeyer, P-Y. (2013)
Proceedings of IEEE International Conference on Development and Learning and Epigenetic Robotics, IEEE ICDL-Epirob, Osaka, Japan.
http://hal.archives-ouvertes.fr/docs/…

Learning human motion primitives with multimodal non-negative matrix factorization. Read more...

Learning combinatorial human motion primitives with multimodal non-negative matrix factorization

Keywords: imitation learning, robotics, human behavior understanding, motion primitive, dictionary learning, multimodal learning, dance

We present an approach, based on non-negative matrix factorization, for learning to recognize parallel combinations of initially unknown human motion primitives, associated with ambiguous sets of linguistic labels during training. In the training phase, the learner observes a human producing complex motions which are parallel combinations of initially unknown motion primitives. Each time the human shows a complex motion, he also provides high-level linguistic descriptions, consisting of a set of labels giving the name of the primitives inside the complex motion. From the observation of multi-modal combinations of high-level labels with high-dimensional continuous unsegmented values representing complex motions, the learner must later on be able to recognize, through the production of the adequate set of labels, which are the motion primitives in a novel complex motion produced by a human, even if those combinations were never observed during training. We explain how this problem, as well as natural extensions, can be addressed using non-negative matrix factorization. Then, we show in an experiment in which a learner has to recognize the primitive motions of complex human dance choreographies, that this technique allows the system to infer with good performance the combinatorial structure of parallel combinations of unknown primitives.

More details can be found in the paper :
Mangin O., Oudeyer P.Y., Learning to recognize parallel combinations of human motion primitives with linguistic descriptions using non-negative matrix factorization. IEEE/RSJ International Conference on Intelligent Robots and Systems, Vilamoura, Algarve (Portugal), 2012.
http://olivier.mangin.com/publi.html#…
https://flowers.inria.fr/ManginOudeye…

A formal approach to social learning: Exploring language acquisition through imitation. Read more...

A formal approach to social learning: Exploring language acquisition through imitation
Presentation made by Thomas Cederborg for his PhD viva, december 2013.

This presentation covers topics presented in details in the following research articles:

From Language to Motor Gavagai: Unified Imitation Learning of Multiple Linguistic and Non-linguistic Sensorimotor Skills
Thomas Cederborg; Pierre-Yves Oudeyer
IEEE Transactions on Autonomous Mental Development (TAMD), IEEE, 2013
https://flowers.inria.fr/CederborgOud…

Simultaneous Acquisition of Task and Feedback Models
Manuel Lopes; Thomas Cederborg; Pierre-Yves Oudeyer
Development and Learning (ICDL), 2011 IEEE International Conference on, 2011, Germany. Development and Learning (ICDL), 2011 IEEE International Conference on, pp. 1 – 7
http://hal.archives-ouvertes.fr/docs/…

Imitating Operations On Internal Cognitive Structures for Language Aquisition
Thomas Cederborg; Pierre-Yves Oudeyer
HUMANOIDS, 2011, Bled, Slovenia. HUMANOIDS Proceedings, pp. NA
http://hal.archives-ouvertes.fr/docs/…

Incremental Local Online Gaussian Mixture Regression for Imitation Learning of Multiple Tasks
Thomas Cederborg; Adrien Baranes; Li Ming; Pierre-Yves Oudeyer
International Conference On Intelligent Robots and Systems (IROS), 2010, Taipei, Taiwan, Province Of China.
https://flowers.inria.fr/Cederborgeta…

The Ergo-Robot Experiment: Artificial Curiosity and Language Formation in Robots Read more...

The Ergo-Robot Experiment: Artificial Curiosity and Language Formation in Robots

Presentation of the Ergo-Robot Experiment by Pierre-Yves Oudeyer, during “Symposium on Language Acquisition and Language Evolution”, Stockholm University, Royal Academy of Sciences, Stockholm, Sweden (organised by Francesco Lacerda and Bjorn Lindblom).

=== Summary

In a big egg that has just opened, a tribe of young robotic creatures evolves and explores its environment, wreathed by a large zero that symbolizes the “origin.” Beyond their innate capabilities, they are outfitted with mechanisms that allow them to learn new skills and invent their own language. Endowed with artificial curiosity, they explore objects around them, as well as the effect their vocalizations produce on humans. Human, also curious to see what these creatures can do, react with their own gestures, creating a loop of interaction which progressively self-organizes into a new communication system established between man and ergo-robots.

The Ergo-Robot Experiment addresses a very important methodological and experimental need in Developmental Robotics: evaluating how algorithmic architectures for learning and development can scale up to long-term real world robot experiments (i.e. robot operating and learning continuously for several weeks or months). For this goal, which Ergo-Robots addresses [P28], and in the context of a research lab, one needs an experimental platform which is very robust, with precise and reliable motor control, easy to use and maintain, relatively cheap, and reconfigurable (in order to evaluate algorithms on robots with different morphologies, i.e. different robots).

The experiment was presented at the exhibition “Mathematics: A Beautiful Elsewhere” at Fondation Cartier pour l’Art Contemporain (scenography made in collaboration with film director David Lynch) provided in itself a large impact for scientific dissemination of our research activities towards the general public, being explained by student scientific mediators to around 70000 visitors (trained students were continuously present in the exhibition), and being reported multiple times in the general press (e.g. France 2, France Inter, France Culture, RFI, BFM TV, Slate.fr, Sciences et Avenir, New Scientist, Financial Times).

ts software and hardware development was realized by the INRIA ENSTA ParisTech Flowers team in collaboration with University of Bordeaux/Labri: Jérome Béchu, Fabien Bénureau, Haylee Fogg, Paul Fudal, Hugo Gimbert, Matthieu Lapeyre, Olivier Ly, Olivier Mangin, Pierre-Yves Oudeyer, Pierre Rouanet. Scenography was realized in collaboration with David Lynch and his team. Scenography was realiszed in collaboration with David Lynch and his team.

=== Main references

Web site: https://flowers.inria.fr/robots/ergo-robots/

Oudeyer, P-Y. (2011) Curiosity and Languages, in Catalogue of the Exhibition “Mathematics: A Beautiful Elsewhere”, Fondation Cartier pour l’Art Contemporain, Paris, France.

https://flowers.inria.fr/OudeyerCatalogueExpoMathematics2011GB.pdf

Oudeyer P-Y, Kaplan , F. and Hafner, V. (2007) Intrinsic Motivation Systems for Autonomous Mental Development, IEEE Transactions on Evolutionary Computation, 11(2), pp. 265–286.

http://www.pyoudeyer.com/ims.pdf

Steels, L. (2003) Evolving grounded communication for robots. Trends in Cognitive Science. 7(7), July 2003, pp. 308-312.

http://www.csl.sony.fr/downloads/papers/2003/steels-03c.pdf

Gottlieb, J., Oudeyer, P-Y., Lopes, M., Baranes, A. (2013)
Trends in Cognitive Science, 17(11), pp. 585-596. http://dx.doi.org/10.1016/j.tics.2013.09.001


Talks et interviews (français)

Quand les robots nous aident à comprendre l'homme

Quand les robots nous aident à comprendre l’homme: Le corps comme variable expérimentale

Présentation de Pierre-Yves Oudeyer à la conférence LIFT Marseille, octobre 2013

Pierre Yves Oudeyer, directeur de recherche à l’Inria, s’appuie sur des robots pour aller chercher la réponse à quelques questions essentielles : Qu’est-ce que marcher et comment cela s’apprend-il ? Comment apprendre par soi-même ? Comment naissent les langues ? Et pour permettre à d’autres de poser leurs propres questions, il nous présente Poppy, “le premier robot humanoïde DIY open-source”.

(This work by Lift Conference is licensed under a Creative Commons Attribution-ShareAlike 2.5 Switzerland License. Original link: http://videos.liftconference.com/video/9039672/0/comment-les-robots-nous-aident-a)

Comment s'invente le langage ? En lire plus...

Comment s’invente le langage ?

Interview de Pierre-Yves Oudeyer autour du livre « Aux sources de la parole », Odile Jacob.

Site web du livre: http://www.pyoudeyer.com/AuxSourcesDe…

Quelles sont les origines de la parole ? Comment les premières vocalisations organisées, partagées culturellement par un groupe d’individus, sont elles nées ? Comment un individu découvre-t-il la parole au cours de l’apprentissage ?

Ce livre explore le rôle de l’auto-organisation dans l’évolution et le développement de la parole. Traçant un parallèle avec la formation spontanée de structures dans le monde inorganique, comme celle des cristaux de glace, il étudie comment des systèmes vocaux peuvent s’auto-organiser, sans plan pré-établi, au cours d’interactions élémentaires et répétées entre des individus qui n’ont pas déjà un langage.

Il étudie aussi comment, au cours du développement de l’individu, le babillage et l’imitation vocale peuvent eux-mêmes s’auto-organiser, résultant d’un mécanisme de curiosité, motivation intrinsèque qui pousse le nourrisson à découvrir son corps et ses interactions avec l’environnement par pur plaisir d’apprendre.

Quand les sciences informatiques permettent d’éclairer d’un jour nouveau la nature et l’évolution du langage.

Cette exploration est ici réalisée in silico, avec des modèles informatiques et robotiques, qui permettent, en dialogue constant avec les sciences du vivant et de l’homme, de mieux comprendre les rôles respectifs du corps, du babillage, de l’apprentissage, de l’imitation, et les dynamiques non-linéaires de leurs interactions.

Le livre étudie en particulier comment une population d’individus robotiques peut créer, former, négotier son propre système de vocalisations au cours d’interactions pair à pair, et les compare aux systèmes humains. Il discute également comment il est possible de modéliser des mécanismes de curiosité permettant à un robot d’explorer et de découvrir son corps et ses interactions avec l’environnement physique et social.

Ainsi se forme une vision dans laquelle des mécanismes auto-organisés viennent compléter ceux de la sélection naturelle. Des cartes nouvelles se dessinent, et nous montrent des chemins jusqu’alors inconnus pour remonter aux sources de la parole.

Auteur

Pierre-Yves Oudeyer, directeur de recherche à Inria, étudie les mécanismes du développement sensori-moteur, cognitif et social chez l’humain et chez les robots. Suivant une approche multidisciplinaire, où les sciences du numérique par- ticipent à notre compréhension du vivant et de l’homme, il s’intéresse au rôle de l’auto-organisation et de l’apprentissage au cours des interactions entre cerveau, corps et environnement physique et social.

Lauréat du programme européen ERC et du prix Le Monde de la recherche universitaire, il dirige l’équipe Flowers à Inria et à l’Ensta ParisTech, et a été chercheur au Sony Computer Science Laboratory à Paris.

Emission « Autour de la question », de Caroline Lachowsky, 9 sept. 2013

Où vont les robots ? Les défis de la robotique personnelle au 21ème siècle. En lire plus...

“Où vont les robots?”, Journée “Des robots et des hommes”, Cité des Sciences et de l’Industrie, 2010 (Vulgarisation / Médiation scientifique).

OU VONT LES ROBOTS ? QUELQUES DEFIS DE LA ROBOTIQUE PERSONNELLE, par Pierre-Yves Oudeyer
http://www.pyoudeyer.com

Plan de la présentation:
Introduction
A. LE DEVELOPPEMENT DES ROBOTS – BREF RAPPELS HISTORIQUES

1. La préhistoire technique de la robotique
2. Les premiers vrais robots et l’invention de l’ordinateur
3. Robo Industrialus
4. Robo Exploratius
5. Robo Mobilis
6. Robo Domesticus Servicius
7. Robo Domesticus Socialus
8. Impact sociétal et économique futur
9. La disparition future de la distinction entre l’humain et la machine : la singularité
10. L’éthique et l’intégration des robots dans la société future

B. LA FICTION, LES DEFIS, LE PROGRES

1. Les défis à relever :
– communication avec les robots
– pertinence de la conduite
– robustesse
– apprentissage

Les domaines de recherche en développement :
– intelligence artificielle
– robotique
– programme simulant la pensée de l’enfant

C. LES ROBOTS CAPABLES D’APPRENDRE

1. L’apprentissage de mots et de sens nouveaux
2. Le partage de l’attention
3. L’apprentissage de savoirs-faire moteurs :
– procédures par imitation-démonstration
– exploration spontanée des interactions avec l’environnement physique

6. Conclusion : la science est très très loin derrière la fiction….

LES QUESTIONS DU PUBLIC
avec Jean-Claude Heudin et Pierre-Yves Oudeyer

L’apprentissage d’un robot peut-il être récupéré et transmis à un autre robot ?
Pouvez-vous donner une caractéristique de l’intelligence ?
Une imitation de l’affectif est-elle possible ?
Quelle est l’origine et la signification du mot robot ?
Quel est l’état de l’art des interfaces entre l’électronique et les cellules ?
La robotique est-elle un phénomène de mode ou un besoin réel ?

Lien original: http://www.cite-sciences.fr/fr/confer…

Des robots qui inventent leur propre langue. En lire plus...

Extrait de:
Mirouze, J-P. (2002) Images et sciences du langage (Interview de PY Oudeyer, 10 mn), Broadcasted on France 5 (and used as a support in schools).

Il y a très longtemps, les humains ne produisaient que des grognements inarticulés. La question de savoir comment ils en sont venus à parler est l’une des interrogations les plus difficiles qui soit posée à la science. La robotique peut nous aider.

Liens:
Aux sources de la parole: auto-organisation et évolution
Oudeyer, P-Y. (sept. 2013)
Odile Jacob, Paris.
http://www.pyoudeyer.com/AuxSourcesDe…

Alan Turing et la robotique développementale. En lire plus...

Alan Turing et la robotique développementale.
Interview de PY Oudeyer

En 1950, dans son article Computing Machinery and Intelligence, Alan Turing proposait pour la première fois l’idée de construire une machine qui apprendrait comme un enfant : « Plutôt que d’écrire un programme qui simulerait le fonctionnement mental d’un adulte, pourquoi ne pas en produire un qui simulerait celui d’un enfant ? Si celui-ci suivait alors une éducation appropriée, alors on pourrait obtenir un cerveau adulte. » Cette idée est restée longtemps presque inexplorée, et ce n’est que depuis une quinzaine d’années qu’elle est devenue le centre d’un nouveau domaine scientifique : la « robotique développementale ». Ce nouveau champ est dédié à l’étude et à la modélisation informatique et mathématique des processus du développement sensorimoteurs et social.

L'auto-organisation dans l'évolution de la parole, College de France, 2008. En lire plus

Conférence de Pierre-Yves Oudeyer, “L’auto-organisation dans l’évolution de la parole”, dans le cadre du Colloque de rentrée du Collège de France “Aux Origines du Dialogue Humain: Parole et Musique” à Paris, octobre 2008.

Résumé:
Les systèmes de vocalisations humains, véhicules physiques du langage, sont caractérisés par des formes et des propriétés structurales complexes. Ils sont combinatoriaux, basés sur la ré-utilisation systématique de phonèmes, et l’ensemble des répertoires de phonèmes des langues du monde est marqué à la fois par de fortes régularités statistiques, les universaux, et une grande diversité. En outre, ce sont des codes culturellement partagés par chaque communauté de locuteurs. Quelle est l’origine des formes de la parole ? Quels sont les mécanismes qui, au cours de la phylogenèse et de l’évolution culturelle, ont permis leur évolution ? Comment un code de la parole partagé peut-il se former dans une communauté d’individus ? Je vais m’intéresser dans ce chapitre à la manière dont les phénomènes d’auto-organisation, et leurs interactions avec la sélection naturelle, peuvent permettre d’éclairer ces trois questions.
La tendance qu’ont de nombreux systèmes physiques complexes à générer spontanément des formes nouvelles et organisées, comme les cristaux de glaces ou les spirales galactiques, est présente en effet tout autant dans le monde inorganique que dans le monde vivant. Ainsi, l’explication de l’origine des formes du vivant ne peut reposer uniquement sur le principe de sélection naturelle, qui doit être complémenté par la compréhension des mécanismes de génération de formes nouvelles dans lesquels l’auto-organisation est centrale. Or, ceci s’applique aux formes sociales et culturelles du vivant, en particulier aux formes de la parole et du langage. Je vais donc ainsi commencer par articuler de manière générale les relations entre auto-organisation, sélection naturelle et néo-Darwinisme pour la compréhension de la genèse des formes du vivant. Je vais ensuite instancier ces relations dans le cadre des trois questions que j’ai énoncées ci-dessus. J’expliquerai alors pourquoi l’utilisation de simulations et de modèles informatiques est fondamentale pour faire progresser les théories qui y sont afférentes. Enfin, je présenterai un exemple d’expérimentation d’un modèle informatique qui montre que certains mécanismes simples de couplages sensorimoteurs permettent de générer des systèmes de parole combinatoriaux, caractérisés par la dualité universaux/diversité, et partagés culturellement. Je conclurai par les scénarios évolutionnaires que cette expérimentation informatique vient complémenter ou renouveler.

Oudeyer, P-Y. (2009) L’auto-organisation dans l’évolution de la parole, in Dehaene, S., and Petit, C., Parole et Musique: Aux origines du dialogue humain, Colloque annuel du Collège de France, pp. 83-112, Odile Jacob.
http://www.pyoudeyer.com/ParoleetMusi

Aux sources de la parole: auto-organisation et évolution
Oudeyer, P-Y. (sept. 2013)
Odile Jacob, Paris.
http://www.pyoudeyer.com/AuxSourcesDe